Machine Learning Identification of Modifiable Predictors of Patient Outcomes After Transcatheter Aortic Valve Replacement

Transcatheter aortic valve replacement (TAVR) is an important treatment option for patients with severe symptomatic aortic stenosis. It is important to identify predictors of excellent outcomes (good clinical outcomes, more time spent at home) after TAVR that are potentially amenable to improvement....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:JACC. Advances (Online) Ročník 3; číslo 8; s. 101116
Hlavní autoři: Russo, Mark J., Elmariah, Sammy, Kaneko, Tsuyoshi, Daniels, David V., Makkar, Rajendra R., Chikermane, Soumya G., Thompson, Christin, Benuzillo, Jose, Clancy, Seth, Pawlikowski, Amber, Lawrence, Skye, Luck, Jeff
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Elsevier Inc 01.08.2024
Elsevier
Témata:
artificial intelligence
cardiology
Cardiovascular
care process
Original Research
patient-centered
random forest
TAVR
care process
SHAP
random forest
artificial intelligence
cardiology
TAVR
AUC
patient-centered
LOS
AS
STS
RF
ML
Shapley Additive Explanation
area under the curve
machine learning
aortic stenosis
length of stay
Society of Thoracic Surgeons
transcatheter aortic valve replacement
ISSN:2772-963X, 2772-963X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Transcatheter aortic valve replacement (TAVR) is an important treatment option for patients with severe symptomatic aortic stenosis. It is important to identify predictors of excellent outcomes (good clinical outcomes, more time spent at home) after TAVR that are potentially amenable to improvement. The purpose of the study was to use machine learning to identify potentially modifiable predictors of clinically relevant patient-centered outcomes after TAVR. We used data from 8,332 TAVR cases (January 2016-December 2021) from 21 hospitals to train random forest models with 57 patient characteristics (demographics, comorbidities, surgical risk score, lab values, health status scores) and care process parameters to predict the endpoint, a composite of parameters that designated an excellent outcome and included no major complications (in-hospital or at 30 days), post-TAVR length of stay of 1 day or less, discharge to home, no readmission, and alive at 30 days. We used recursive feature elimination with cross-validation and Shapley Additive Explanation feature importance to identify parameters with the highest predictive values. The final random forest model retained 29 predictors (15 patient characteristics and 14 care process components); the area under the curve, sensitivity, and specificity were 0.77, 0.67, and 0.73, respectively. Four potentially modifiable predictors with relatively high Shapley Additive Explanation values were identified: type of anesthesia, direct movement to stepdown unit post-TAVR, time between catheterization and TAVR, and preprocedural length of stay. This study identified 4 potentially modifiable predictors of excellent outcome after TAVR, suggesting that machine learning combined with hospital-level data can inform modifiable components of care, which could support better delivery of care for patients undergoing TAVR. [Display omitted]
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2772-963X
2772-963X
DOI:10.1016/j.jacadv.2024.101116